[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAVP68SMEX39MAQW6DCB2Z":3,"skill-same:01M6DAVP68SMEX39MAQW6DCB2Z":102},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":13,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6DAVP68SMEX39MAQW6DCB2Z","skill-standards",null,"Use when creating, updating, reviewing, or auditing a skill or superskill and you need a concrete quality bar for triggers, project grounding, metadata, authorship, routing, context efficiency, scripts, and validation.","tzeusy-org\u002Fai-bootstrap","tzeusy-org","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F141543652?v=4","01M6DAM1AP09H27BYGFY9QCNPB","01M6DAM1F4R187EK11XDN9JZKH",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-engineering\u002Fsubskills\u002Fskill-standards\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"skill standards","standards","use","triggers","openai codex","project","efficiency","active","uv","codex","context","quality","audit","metadata","openai","validation","routing","run","2026-11-10 10:12:30",false,"---\nname: skill-standards\ndescription: Use when creating, updating, reviewing, or auditing a skill or superskill and you need a concrete quality bar for triggers, project grounding, metadata, authorship, routing, context efficiency, scripts, and validation.\nmetadata:\n  owner: tze\n  authors:\n    - tze\n    - OpenAI Codex\n    - Claude\n    - Claude Fable 5.1\n  status: active\n  last_reviewed: \"2026-10-03\"\ncompatibility: Requires uv to run scripts\u002Faudit_skill.py.\n---\n\n# Skill Standards\n\nReview bar for new skills and updates to existing ones, including\nrouter-style superskills.\n\nThe standard: easy to discover, cheap to load, grounded in the right source\nof truth, explicit about who owns it.\n\n## Use This Skill When\n\n- Creating a new skill; you want a quality bar before shipping it\n- Reviewing or auditing a skill for discoverability, grounding, context\n  efficiency, and maintainability\n- Updating a skill; checking for drift, bloat, or stale metadata\n- Designing a superskill that routes to internal subskills without putting\n  every subskill in the global skill catalog\n\nExample trigger phrasings: \"review this skill\", \"is this SKILL.md well\ndesigned\", \"audit our skills for quality\", \"should this be a superskill\",\n\"clean up this skill package\".\n\n## Do Not Use This Skill For\n\n- Replacing the sibling [skill-creator](..\u002Fskill-creator\u002FSKILL.md) subskill for initial scaffolding or end-to-end authoring\n- Replacing project-specific doctrine or navigation skills such as\n  `\u002Fth-projects`\n- Acting as the domain skill itself; this is a rubric for skill quality, not\n  domain guidance\n- Measuring whether installed skills are actually *used* and archiving dead\n  ones — `\u002Fth-tooling` (audit-skill-hygiene); this skill judges content\n  quality, not catalog hygiene\n\n## Workflow\n\n1. Run the mechanical audit\n   [`scripts\u002Faudit_skill.py`](.\u002Fscripts\u002Faudit_skill.py) first — it checks\n   frontmatter, name\u002Fdescription limits, metadata fields, link integrity,\n   orphaned support files and deep reference chains, PEP 723 compliance of\n   Python entry-point scripts, adapter YAML, and superskill layout:\n\n   ```bash\n   uv run \u003Cthis-package>\u002Fscripts\u002Faudit_skill.py \u003Ctarget-skill-dir>\n   ```\n\n   Resolve `\u003Cthis-package>` from the path of the `SKILL.md` you loaded —\n   this subskill lives under the `th-engineering` package's `subskills\u002F`,\n   not a global skills directory.\n\n   Fix every ERROR. Triage WARNs deliberately — fix or justify. Any Python\n   helper script flagged for missing PEP 723 inline metadata must be brought\n   into compliance as part of the change, not left for later (see\n   quality-bar section 8 for the required header).\n2. Read the target skill's `SKILL.md` and any support files it references.\n   For project-specific skills, read the relevant project-shape docs first\n   (via `\u002Fth-projects`) so the skill stays aligned with the repo's actual\n   doctrine, topology, and spec surface.\n3. Judge what the script cannot, using\n   [`references\u002Fquality-bar.md`](.\u002Freferences\u002Fquality-bar.md):\n   trigger quality, scope sharpness, project grounding, progressive\n   discovery, script-vs-prose decisions, runtime token economics of\n   prescribed commands (projected output, log-tail readback, targeted\n   gates, grep-first catalogs), operational safety, maintenance\n   contracts on stateful reference docs (catalogs of errors, projects, or\n   quirks must tell consuming agents when to write back), and fit to\n   current models (section 12: reasons over personas, effort tiers,\n   uncapped review prompts, explicit delegation and stop conditions,\n   legible output).\n4. Use [`references\u002Fsuperskills.md`](.\u002Freferences\u002Fsuperskills.md) only when\n   the skill is broad enough to route over internal workflows rather than run\n   a single narrow procedure.\n5. Follow [`references\u002Freview-checklist.md`](.\u002Freferences\u002Freview-checklist.md)\n   for the update procedure, verification steps, and anti-patterns.\n6. Keep `SKILL.md`, tool-specific adapter files (e.g. `agents\u002Fopenai.yaml`),\n   and referenced support files aligned. If the skill still reads as a\n   monolith after review, split heavy guidance into direct support files\n   instead of appending more prose.\n","# Skill Standards\n\nReview bar for new skills and updates to existing ones, including\nrouter-style superskills.\n\nThe standard: easy to discover, cheap to load, grounded in the right source\nof truth, explicit about who owns it.\n\n## Use This Skill When\n\n- Creating a new skill; you want a quality bar before shipping it\n- Reviewing or auditing a skill for discoverability, grounding, context\n  efficiency, and maintainability\n- Updating a skill; checking for drift, bloat, or stale metadata\n- Designing a superskill that routes to internal subskills without putting\n  every subskill in the global skill catalog\n\nExample trigger phrasings: \"review this skill\", \"is this SKILL.md well\ndesigned\", \"audit our skills for quality\", \"should this be a superskill\",\n\"clean up this skill package\".\n\n## Do Not Use This Skill For\n\n- Replacing the sibling [skill-creator](..\u002Fskill-creator\u002FSKILL.md) subskill for initial scaffolding or end-to-end authoring\n- Replacing project-specific doctrine or navigation skills such as\n  `\u002Fth-projects`\n- Acting as the domain skill itself; this is a rubric for skill quality, not\n  domain guidance\n- Measuring whether installed skills are actually *used* and archiving dead\n  ones — `\u002Fth-tooling` (audit-skill-hygiene); this skill judges content\n  quality, not catalog hygiene\n\n## Workflow\n\n1. Run the mechanical audit\n   [`scripts\u002Faudit_skill.py`](.\u002Fscripts\u002Faudit_skill.py) first — it checks\n   frontmatter, name\u002Fdescription limits, metadata fields, link integrity,\n   orphaned support files and deep reference chains, PEP 723 compliance of\n   Python entry-point scripts, adapter YAML, and superskill layout:\n\n   ```bash\n   uv run \u003Cthis-package>\u002Fscripts\u002Faudit_skill.py \u003Ctarget-skill-dir>\n   ```\n\n   Resolve `\u003Cthis-package>` from the path of the `SKILL.md` you loaded —\n   this subskill lives under the `th-engineering` package's `subskills\u002F`,\n   not a global skills directory.\n\n   Fix every ERROR. Triage WARNs deliberately — fix or justify. Any Python\n   helper script flagged for missing PEP 723 inline metadata must be brought\n   into compliance as part of the change, not left for later (see\n   quality-bar section 8 for the required header).\n2. Read the target skill's `SKILL.md` and any support files it references.\n   For project-specific skills, read the relevant project-shape docs first\n   (via `\u002Fth-projects`) so the skill stays aligned with the repo's actual\n   doctrine, topology, and spec surface.\n3. Judge what the script cannot, using\n   [`references\u002Fquality-bar.md`](.\u002Freferences\u002Fquality-bar.md):\n   trigger quality, scope sharpness, project grounding, progressive\n   discovery, script-vs-prose decisions, runtime token economics of\n   prescribed commands (projected output, log-tail readback, targeted\n   gates, grep-first catalogs), operational safety, maintenance\n   contracts on stateful reference docs (catalogs of errors, projects, or\n   quirks must tell consuming agents when to write back), and fit to\n   current models (section 12: reasons over personas, effort tiers,\n   uncapped review prompts, explicit delegation and stop conditions,\n   legible output).\n4. Use [`references\u002Fsuperskills.md`](.\u002Freferences\u002Fsuperskills.md) only when\n   the skill is broad enough to route over internal workflows rather than run\n   a single narrow procedure.\n5. Follow [`references\u002Freview-checklist.md`](.\u002Freferences\u002Freview-checklist.md)\n   for the update procedure, verification steps, and anti-patterns.\n6. Keep `SKILL.md`, tool-specific adapter files (e.g. `agents\u002Fopenai.yaml`),\n   and referenced support files aligned. If the skill still reads as a\n   monolith after review, split heavy guidance into direct support files\n   instead of appending more prose.\n",{"name":5,"metadata":46,"description":7,"compatibility":53},{"owner":47,"status":30,"authors":48,"last_reviewed":52},"tze",[47,49,50,51],"OpenAI Codex","Claude","Claude Fable 5.1","2026-10-03","Requires uv to run scripts\u002Faudit_skill.py.","main","c907d6f0bf96bd61b936e8972e0f1c66ebb8148c","skills\u002Fpersonal\u002Fth-engineering\u002Fsubskills\u002Fskill-standards","https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap","https:\u002F\u002Fgithub.com\u002Ftzeusy-org","2026-11-10 23:17:25",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add tzeusy-org\u002Fai-bootstrap --skill skill-standards",{"tool":66,"command":67},"bunx","bunx skills add tzeusy-org\u002Fai-bootstrap --skill skill-standards",{"tool":69,"command":70},"pnpm","pnpm dlx skills add tzeusy-org\u002Fai-bootstrap --skill skill-standards","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-engineering\u002Fsubskills\u002Fskill-standards\u002FSKILL.md",true,[74,80,84,88,92,98],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"agents\u002Fopenai.yaml","REFERENCE","参考文档",428,"https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-engineering\u002Fsubskills\u002Fskill-standards\u002Fagents\u002Fopenai.yaml",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fquality-bar.md",17043,"https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-engineering\u002Fsubskills\u002Fskill-standards\u002Freferences\u002Fquality-bar.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Freview-checklist.md",5309,"https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-engineering\u002Fsubskills\u002Fskill-standards\u002Freferences\u002Freview-checklist.md",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fsuperskills.md",5684,"https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-engineering\u002Fsubskills\u002Fskill-standards\u002Freferences\u002Fsuperskills.md",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Faudit_skill.py","SCRIPT","脚本",15213,"https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-engineering\u002Fsubskills\u002Fskill-standards\u002Fscripts\u002Faudit_skill.py",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"tests\u002Frun_tests.py",3974,"https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-engineering\u002Fsubskills\u002Fskill-standards\u002Ftests\u002Frun_tests.py",[103,126,151,166,185,196],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":41},"01M6DAZD21TWH2ET70V9FF75CQ","user-run","Use when a step needs privileges this session lacks (docker, sudo, another user's checkout or secrets, host access) and the owner must run it as tze. Writes a reviewable \u002Fhome\u002Forca\u002F.tmp\u002F\u003Cslug>\u002Frun.sh that impersonates tze (USER_TO_IMPERSONATE overrides), tees timestamped logs plus latest.log and collects artifacts there; Claude presents it with a risk and time brief, then continues from the logs. Triggers: \"I'll run it for you\", \"permission denied on docker.sock\", \"needs sudo\", \"sudo: a password is required\", \"run as tze\", \"\u002Fuser-run\".","https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fuser-run\u002FSKILL.md",[],[110,111,40,112,113,25,114,115,26,116,30,117,118,119,120,121,122,123,124,125],"user run","user","docker","logs","host","as","permission","time","log","artifacts","session","password","access","secrets","risk","brief",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":140,"publishedAt":41},"01M6DAZAHTCBAD2WF0GAHWPST8","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-workflow\u002Fsubskills\u002Frequesting-code-review\u002FSKILL.md",[132,135],{"categoryNo":133,"categoryName":134,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":136,"categoryName":137,"taxonomyType":138,"taxonomyTypeDesc":139},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[141,142,143,144,145,146,30,147,148,25,149,150],"requesting code review","code","review","code review","work","requirements","upstream","superpowers","verify","tasks",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":159,"publishedAt":41},"01M6DAZ7CJ82D81XZB2YHVVY48","receiving-code-review","Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation","https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-workflow\u002Fsubskills\u002Freceiving-code-review\u002FSKILL.md",[157,158],{"categoryNo":133,"categoryName":134,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":136,"categoryName":137,"taxonomyType":138,"taxonomyTypeDesc":139},[160,142,143,144,30,147,161,148,25,162,163,164,165],"receiving code review","implementation","code review feedback","technical","feedback","verification",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":41},"01M6DAZ4ER76ADXJ9KRFP7V3Q9","finishing-a-development-branch","Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup","https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-workflow\u002Fsubskills\u002Ffinishing-a-development-branch\u002FSKILL.md",[],[173,174,175,176,25,177,145,178,179,180,148,181,182,183,30,147,184,161],"branch","development","finishing a development branch","integrate","decide","how","cleanup","pr","merge","tests","structured","options",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":191,"publishedAt":41},"01M6DAYZFWWW2YPKP89QNQR96H","executing-plans","Use when you have a written implementation plan to execute in a separate session with review checkpoints","https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-workflow\u002Fsubskills\u002Fexecuting-plans\u002FSKILL.md",[],[192,193,194,143,195,30,147,161,148,25,120],"plans","executing plans","plan","execute",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":202,"publishedAt":41},"01M6DAYWM2YQHYCK7C35K1D29J","dispatching-parallel-agents","Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies","https:\u002F\u002Fgithub.com\u002Ftzeusy-org\u002Fai-bootstrap\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fth-workflow\u002Fsubskills\u002Fdispatching-parallel-agents\u002FSKILL.md",[],[203,204,205,25,148,147,206,30,207,150,208],"parallel agents","parallel","dispatching parallel agents","state","dependencies","shared"]